Last active
December 10, 2015 00:29
-
-
Save woodywang/4351448 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package cn.com.admaster.hadoop.compress; | |
import com.hadoop.compression.lzo.LzopCodec; | |
import org.apache.hadoop.fs.Path; | |
import org.apache.hadoop.io.LongWritable; | |
import org.apache.hadoop.io.Text; | |
import org.apache.hadoop.mapreduce.Job; | |
import org.apache.hadoop.mapreduce.Mapper; | |
import org.apache.hadoop.mapreduce.Reducer; | |
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; | |
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; | |
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; | |
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; | |
import java.io.IOException; | |
/** | |
* Created with IntelliJ IDEA. | |
* User: woody | |
* Date: 12/21/12 | |
* Time: 1:43 PM | |
* To change this template use File | Settings | File Templates. | |
*/ | |
public class Lzo { | |
public static void main(String[] args) throws Exception { | |
if (args.length < 2) { | |
System.err.println("Usage: Lzo <input path> <output path>"); | |
System.exit(-1); | |
} | |
Job job = new Job(); | |
job.setJarByClass(Lzo.class); | |
job.setNumReduceTasks(1); | |
job.setMapperClass(LzoMapper.class); | |
job.setMapOutputKeyClass(LongWritable.class); | |
job.setMapOutputValueClass(Text.class); | |
job.setReducerClass(LzoReducer.class); | |
job.setOutputKeyClass(Text.class); | |
job.setOutputValueClass(Text.class); | |
job.setInputFormatClass(TextInputFormat.class); | |
job.setOutputFormatClass(TextOutputFormat.class); | |
FileInputFormat.addInputPath(job, new Path(args[0])); | |
FileOutputFormat.setOutputPath(job, new Path(args[1])); | |
FileOutputFormat.setCompressOutput(job, true); | |
FileOutputFormat.setOutputCompressorClass(job, LzopCodec.class); | |
job.setJobName("Lzo Compression: " + args[1]); | |
System.exit(job.waitForCompletion(true) ? 0 : 1); | |
} | |
static class LzoMapper extends Mapper<LongWritable, Text, LongWritable, Text> { | |
@Override | |
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { | |
String line = value.toString().trim(); | |
if (line.length() > 0) { | |
context.write(key, value); | |
} | |
} | |
} | |
static class LzoReducer extends Reducer<LongWritable, Text, Text, Text> { | |
@Override | |
public void reduce(LongWritable key, Iterable<Text> values, Context context) throws IOException, InterruptedException { | |
for (Text v: values) { | |
context.write(null, v); | |
} | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment